國立虎尾科技大學 |

Intelligent Feedforward Control System for Solder Joint Anomaly Prediction in Smart Electronics Manufacturing.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Intelligent Feedforward Control System for Solder Joint Anomaly Prediction in Smart Electronics Manufacturing./
作者:	Cao, Nieqing.
面頁冊數:	1 online resource (161 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
Contained By:	Dissertations Abstracts International85-12B.
標題:	Industrial engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9798383136256

Intelligent Feedforward Control System for Solder Joint Anomaly Prediction in Smart Electronics Manufacturing.
Cao, Nieqing.

Intelligent Feedforward Control System for Solder Joint Anomaly Prediction in Smart Electronics Manufacturing. - 1 online resource (161 pages)

Source: Dissertations Abstracts International, Volume: 85-12, Section: B.

Thesis (Ph.D.)--State University of New York at Binghamton, 2024.

Includes bibliographical references

This research presents a feedforward control system that utilizes predictive anomaly detection frameworks to enhance solder joint quality prediction based on quality data from printing and placing processes. In the context of Surface Mount Technology (SMT), anomalous solder joints compromise the reliability of printed circuit boards (PCBs), leading to material and energy waste and increased rework costs. Consequently, this feedforward control system, which can detect joint anomalies early to prevent the formation of defective solder joints, is crucial to implement in solder paste printing and chip placing procedures. Furthermore, if the underlying reason for the anomalous pattern is identified, it can aid operators in determining the root cause of defective solder joints. The process of solder joint formation is primarily categorized into three phases: solder paste printing, pick and place, and solder reflow. This research aims to predict the quality of solder joints before the solder reflow phase, deploying advanced machine learning techniques. In particular, this research investigates three anomaly prediction strategies. Predictive Anomaly Detection for Solder Joints, which is called the PADS framework, is designed to identify the regions of existence of solder joint defects. The uniqueness of PADS is the utilization of novel features generated from interpreting existing physics-based models and substantial real-world data acquired from SMT inspection machines. Recognizing that over 50% of defects originate at the printing stage, this research introduces a novel framework, XSCAN, aimed at predicting the solder joint defect probabilities from the printed solder paste status. This is accomplished by using a generative adversarial network (GAN) to synthesize additional defect data and segment the feature space of printing indicators using customized decision trees to minimize defect probability prediction error. Addressing the limitations from theory-based and data-driven approaches, this research introduces a hybrid modeling framework named Sim2Joint, which combines physics knowledge-based simulations with the adaptability of data-driven methods. By introducing the Sim2Real concept in the joint domain, Sim2Joint bridges the gap between simulation and real situations by integrating dynamic weights for influence factors with real-world data.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798383136256Subjects--Topical Terms:

679492
Industrial engineering.
Subjects--Index Terms:

Anomaly predictionIndex Terms--Genre/Form:

554714
Electronic books.

Intelligent Feedforward Control System for Solder Joint Anomaly Prediction in Smart Electronics Manufacturing.
LDR:03861ntm a22004097 4500 001 1150200
005 20241022111612.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798383136256
035 $a (MiAaPQ)AAI31296504
035 $a AAI31296504
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Cao, Nieqing. $3 1476640
245 1 0 $a Intelligent Feedforward Control System for Solder Joint Anomaly Prediction in Smart Electronics Manufacturing.
264 0 $c 2024
300 $a 1 online resource (161 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
500 $a Advisor: Yoon, Sang Won.
502 $a Thesis (Ph.D.)--State University of New York at Binghamton, 2024.
504 $a Includes bibliographical references
520 $a This research presents a feedforward control system that utilizes predictive anomaly detection frameworks to enhance solder joint quality prediction based on quality data from printing and placing processes. In the context of Surface Mount Technology (SMT), anomalous solder joints compromise the reliability of printed circuit boards (PCBs), leading to material and energy waste and increased rework costs. Consequently, this feedforward control system, which can detect joint anomalies early to prevent the formation of defective solder joints, is crucial to implement in solder paste printing and chip placing procedures. Furthermore, if the underlying reason for the anomalous pattern is identified, it can aid operators in determining the root cause of defective solder joints. The process of solder joint formation is primarily categorized into three phases: solder paste printing, pick and place, and solder reflow. This research aims to predict the quality of solder joints before the solder reflow phase, deploying advanced machine learning techniques. In particular, this research investigates three anomaly prediction strategies. Predictive Anomaly Detection for Solder Joints, which is called the PADS framework, is designed to identify the regions of existence of solder joint defects. The uniqueness of PADS is the utilization of novel features generated from interpreting existing physics-based models and substantial real-world data acquired from SMT inspection machines. Recognizing that over 50% of defects originate at the printing stage, this research introduces a novel framework, XSCAN, aimed at predicting the solder joint defect probabilities from the printed solder paste status. This is accomplished by using a generative adversarial network (GAN) to synthesize additional defect data and segment the feature space of printing indicators using customized decision trees to minimize defect probability prediction error. Addressing the limitations from theory-based and data-driven approaches, this research introduces a hybrid modeling framework named Sim2Joint, which combines physics knowledge-based simulations with the adaptability of data-driven methods. By introducing the Sim2Real concept in the joint domain, Sim2Joint bridges the gap between simulation and real situations by integrating dynamic weights for influence factors with real-world data.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Industrial engineering. $3 679492
653 $a Anomaly prediction
653 $a Feedforward control
653 $a Machine learning
653 $a Smart manufacturing
653 $a Surface Mount Technology
653 $a System optimization
655 7 $a Electronic books. $2 local $3 554714
690 $a 0546
690 $a 0796
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a State University of New York at Binghamton. $b Systems Science Industrial Engineering. $3 1182293
773 0 $t Dissertations Abstracts International $g 85-12B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31296504 $z click for full text (PQDT)